EMIF-based data transmission method and processor
By introducing a first-in-first-out queue in the EMIF system, the 32-bit data is split into 16-bit data for transmission, which solves the problem of signal interference and low efficiency of EMIF during 32-bit data transmission, and realizes efficient 32-bit data reading and writing operate.
Patent Information
- Application Number
- CN202411099322.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-22
AI Technical Summary
During the 32-bit data transmission, EMIF has a large bus bit width, which leads to increased signal interference and poor signal quality. The prior art usually requires slowing down to solve this problem, but it leads to a decrease in the read and write efficiency of 32-bit data.
By introducing a first-in-first-out queue in the system, using data transmission between the 16-bit asynchronous bus interface and the advanced extensible interface, the 32-bit data is split into two 16-bit data for asynchronous or synchronous transmission, and 32-bit data is realized with the help of data cache Efficient read and write operations of bit data.
On the premise of ensuring the quality of 32-bit data signals, the 32-bit data reading and writing efficiency of EMIF is improved, signal interference is reduced, data loss is avoided, and there is no need to modify the bus bit width.
Smart Images

Figure CN119003419A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data transmission, and in particular to an EMIF-based data transmission method and processor. Background Art
[0002] EMIF (External Memory Interface) is an interface technology used to connect processors and external devices. EMIF allows processors to exchange data with external devices through the bus to implement data reading and writing operations. In modern computer systems, EMIF is widely used in various devices, such as microprocessors, embedded systems, and communication equipment. EMIF includes a 16-bit asynchronous bus interface (referred to as a 16-bit interface, supporting the reading and writing of 16-bit data) and a 32-bit asynchronous bus interface (referred to as a 32-bit interface, supporting the reading and writing of 32-bit data). When EMIF reads and writes 32-bit data, the bus width occupied by the 32-bit interface is larger, and the corresponding occupied signal pins will be more, which increases the signal interference and causes the signal quality of data transmission to deteriorate. At present, in order to ensure the signal quality of 32-bit data transmission, the existing technology usually slows down the 32-bit data transmission of EMIF, resulting in reduced efficiency in reading and writing 32-bit data. Summary of the invention
[0003] The present application provides an EMIF-based data transmission method and processor, aiming to improve the 32-bit data reading and writing efficiency of the EMIF.
[0004] In order to achieve the above objectives, this application provides the following technical solutions:
[0005] A data transmission method based on EMIF is applied to a system including a first bus, a data cache and a second bus, wherein the first bus includes a 16-bit asynchronous bus interface of an external device interface, the data cache includes a first-in-first-out queue, and the second bus includes an advanced scalable interface for connecting to an external device, the method includes:
[0006] When the system performs a 32-bit data read operation, the second bus sends the 32-bit data to the first-in-first-out queue;
[0007] The first bus asynchronously obtains two 16-bit data from the first-in-first-out queue to implement the 32-bit data read operation;
[0008] When the system performs a 32-bit data write operation, the first bus splits the 32-bit data into two 16-bit data and asynchronously sends them to the first-in-first-out queue;
[0009] The second bus synchronously obtains two 16-bit data from the first-in-first-out queue to implement the 32-bit data write operation.
[0010] Optionally, the first bus asynchronously obtains two 16-bit data from the first-in-first-out queue to implement the 32-bit data read operation, including:
[0011] The first bus asynchronously obtains two 16-bit data from the first-in-first-out queue according to a preset read timing to implement the 32-bit data read operation;
[0012] Among them, the preset read timing is: after the read operation is responded, it is placed in a waiting state until entering the nth clock cycle, and the first-in-first-out queue is accessed to realize the reading of the first 16-bit data; when the first 16-bit data is successfully read, it is placed in a waiting state again until the end of the mth clock cycle, and the first-in-first-out queue is accessed again to realize the reading of the second 16-bit data; n and m are positive integers, and m is greater than n.
[0013] Optionally, the first bus splits 32-bit data into two 16-bit data and sends the data asynchronously to the first-in-first-out queue, including:
[0014] The first bus splits the 32-bit data into two 16-bit data according to a preset write timing, and sends the data to the first-in-first-out queue asynchronously;
[0015] Among them, the preset write timing is: when the write operation is responded, it is placed in a waiting state until entering the kth clock cycle, and part of the 32-bit data is sent to the first-in-first-out queue to realize the writing of the first 16-bit data; when the first 16-bit data is successfully written, the remaining data in the 32-bit data is sent to the first-in-first-out queue to realize the writing of the second 16-bit data.
[0016] Optionally, the method further includes:
[0017] When the system performs a 16-bit data read operation, the second bus sends the 16-bit data to the first bus.
[0018] Optionally, the method further includes:
[0019] When the system performs a 16-bit data write operation, the first bus sends the 16-bit data to the second bus.
[0020] A processor, comprising:
[0021] A master interface module, a data cache module and a slave interface module;
[0022] Wherein, the master interface module includes a 16-bit asynchronous bus interface for an external device interface, the data cache module includes a first-in-first-out queue, and the slave interface module includes an advanced scalable interface for docking with an external device;
[0023] The slave interface module is used to: send the 32-bit data to the first-in-first-out queue when the processor performs a 32-bit data read operation;
[0024] The main interface module is used to: obtain two 16-bit data from the first-in-first-out queue in sequence to implement the 32-bit data read operation;
[0025] The main interface module is also used for: when the processor performs a 32-bit data write operation, the main interface module splits the 32-bit data into two 16-bit data and asynchronously sends them to the first-in-first-out queue;
[0026] The slave interface module is also used to obtain two 16-bit data in sequence from the first-in-first-out queue to implement the 32-bit data write operation.
[0027] Optionally, the main interface module is specifically used for:
[0028] According to a preset read timing, asynchronously obtain two 16-bit data from the first-in-first-out queue to implement the 32-bit data read operation;
[0029] Among them, the preset read timing is: after the read operation is responded, it is placed in a waiting state until entering the nth clock cycle, and the first-in-first-out queue is accessed to realize the reading of the first 16-bit data; when the first 16-bit data is successfully read, it is placed in a waiting state again until the end of the mth clock cycle, and the first-in-first-out queue is accessed again to realize the reading of the second 16-bit data; n and m are positive integers, and m is greater than n.
[0030] Optionally, the main interface module is specifically used for:
[0031] According to the preset write timing, the 32-bit data is split into two 16-bit data, and sent asynchronously to the first-in-first-out queue;
[0032] Among them, the preset write timing is: when the write operation is responded, it is placed in a waiting state until entering the kth clock cycle, and part of the 32-bit data is sent to the first-in-first-out queue to realize the writing of the first 16-bit data; when the first 16-bit data is successfully written, the remaining data in the 32-bit data is sent to the first-in-first-out queue to realize the writing of the second 16-bit data.
[0033] Optionally, the slave interface module is further used to: send 16-bit data to the master interface module when the processor performs a 16-bit data read operation.
[0034] Optionally, the master interface module is further used to: send 16-bit data to the slave interface module when the processor performs a 16-bit data write operation.
[0035] The technical solution provided by the present application is that when the system performs a 32-bit data read operation, the second bus sends the 32-bit data to a first-in-first-out queue. The first bus asynchronously obtains two 16-bit data from the first-in-first-out queue to implement a 32-bit data read operation. When the system performs a 32-bit data write operation, the first bus splits the 32-bit data into two 16-bit data and sends them asynchronously to the first-in-first-out queue. The second bus synchronously obtains two 16-bit data from the first-in-first-out queue to implement a 32-bit data write operation. The present application uses the first-in-first-out queue provided by the data cache to assist the 16-bit asynchronous bus interface shown in the first bus to realize 32-bit data transmission between the advanced extensible interface shown in the second bus, thereby improving the 32-bit data read and write efficiency of the EMIF while ensuring the signal quality of the 32-bit data. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0037] Figure 1 A schematic diagram of the architecture of a data transmission system provided in an embodiment of the present application;
[0038] Figure 2 A flow chart of a data transmission method based on EMIF provided in an embodiment of the present application;
[0039] Figure 3 A read timing diagram provided for an embodiment of the present application;
[0040] Figure 4 A write timing diagram provided for an embodiment of the present application;
[0041] Figure 5 A schematic diagram of the architecture of a processor provided in an embodiment of the present application. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0043] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0044] like Figure 1 As shown, it is a schematic diagram of the architecture of a data transmission system provided in an embodiment of the present application, including the units shown below.
[0045] A first bus 100 , a data cache 200 and a second bus 300 .
[0046] The first bus 100 includes a 16-bit asynchronous bus interface of EMIF, the data cache 200 includes a FIFO (First in First out), and the second bus 300 includes an AXI (Advanced Extensible Interface) for connecting to external devices.
[0047] FIFO is a traditional sequential execution method, where the first instruction that enters is completed and retired, and then the second instruction is executed (the instruction is the program code that the computer responds to user operations and is transparent to the user).
[0048] AXI is a bus protocol, an on-chip bus for high performance, high bandwidth, and low latency. AXI's address / control and data phases are separated, supporting unaligned data transmission. In burst transmission, only the first address is required, and the separate read and write data channels support transmission access and out-of-order access, making it easier to perform timing convergence. AXI is a new high-performance protocol in AMBA (Advanced Microcontroller Bus Architecture).
[0049] Figure 1 The method for implementing 32-bit data reading and writing in the system shown in the figure can be found in Figure 2 As shown, Figure 2 A flow chart of a data transmission method based on EMIF provided in an embodiment of the present application includes the following steps.
[0050] S201: When the system performs a 32-bit data read operation, the second bus sends the 32-bit data to a first-in-first-out queue.
[0051] Among them, since AXI is a 32-bit data interface, the second bus can be determined to be a 32-bit data bus, and the first bus includes a 16-bit asynchronous bus interface of EMIF, so the first bus can be determined to be a 16-bit data bus.
[0052] It should be noted that, since only 16 bits of data are valid in one clock cycle of the 16-bit data bus of EMIF, and 32 bits of data are valid in one clock cycle of the 32-bit data bus, and two 16-bit data can form one 32-bit data. With the help of FIFO, the first bus and the second bus can flexibly split the 32-bit data into two 16-bit data for transmission, so that the first bus and the FIFO perform 16-bit data transmission, and the second bus and the FIFO perform 32-bit data transmission.
[0053] S202: The first bus asynchronously obtains two 16-bit data from the first-in-first-out queue to implement a 32-bit data read operation.
[0054] Among them, since the first bus is a 16-bit data bus and the first bus supports asynchronous reading and writing of 16-bit data, the first bus can asynchronously obtain two 16-bit data from the first-in-first-out queue to implement a 32-bit data read operation.
[0055] It should be noted that, by using the 16-bit asynchronous bus interface of EMIF, two 16-bit data are asynchronously obtained from the first-in-first-out queue to implement a 32-bit data read operation. Compared with the prior art that uses the 32-bit asynchronous bus interface of EMIF to implement a 32-bit data read operation, the bus width occupied by the first bus is significantly reduced, resulting in less signal interference when the system performs a 32-bit data read operation, and the signal quality is effectively guaranteed. There is no need to modify the bus width during the 32-bit data read operation, and the efficiency of the first bus asynchronously obtaining two 16-bit data from the first-in-first-out queue is not lower than the efficiency of the 32-bit asynchronous bus interface to implement a 32-bit data read operation. In addition, by using the first-in-first-out queue to cache 32-bit data, data loss can also be avoided when the system performs a 32-bit data read operation.
[0056] Optionally, the first bus may asynchronously obtain two 16-bit data from a first-in-first-out queue according to a preset read timing to implement a 32-bit data read operation.
[0057] Optionally, the preset read timing is: after the read operation is responded, it is placed in a waiting state until entering the nth clock cycle, and then the first-in-first-out queue is accessed to realize the reading of the first 16-bit data; when the first 16-bit data is successfully read, it is placed in a waiting state again until the end of the mth clock cycle, and then the first-in-first-out queue is accessed again to realize the reading of the second 16-bit data; n and m are positive integers, and m is greater than n.
[0058] The clock cycle is the most basic and smallest unit of time in a computer, also called an oscillation period, and is defined as the reciprocal of the clock frequency.
[0059] For some examples, see Figure 3 As shown in the read timing, after the read operation is responded, the first bus is placed in a waiting state until entering the 5th clock cycle, and then accesses the first-in-first-out queue to realize the reading of the first 16-bit data; when the first 16-bit data is successfully read, the first bus is placed in a waiting state again until the end of the 8th clock cycle, and then accesses the first-in-first-out queue again to realize the reading of the second 16-bit data.
[0060] exist Figure 3In the timing diagram shown, emif_cen represents the EMIF interface chip select line, emif_addr[15:0] represents the EMIF bus address line, emif_data[15:0] represents the EMIF bus data line, emif_oen represents the EMIF bus read valid bit, emif_wen represents the EMIF bus write valid bit, 1-14 represent each clock cycle, ADDR_low_16bit represents the bus address of the first 16-bit data, ADDR_high_16bit represents the bus address of the second 16-bit data, DATA_low_16bit represents the first 16-bit data, and DATA_high_16bit represents the second 16-bit data.
[0061] S203: When the system performs a 32-bit data write operation, the first bus splits the 32-bit data into two 16-bit data and asynchronously sends them to the first-in-first-out queue.
[0062] Among them, since the first bus is a 16-bit data bus and the first bus supports asynchronous reading and writing of 16-bit data, the first bus can split 32-bit data into two 16-bit data and asynchronously send them to the first-in-first-out queue to implement 32-bit data write operations.
[0063] It should be noted that, by utilizing the 16-bit asynchronous bus interface of EMIF, the 32-bit data is split into two 16-bit data and asynchronously sent to a first-in-first-out queue to implement a 32-bit data write operation. Compared with the prior art of using the 32-bit asynchronous bus interface of EMIF to implement a 32-bit data write operation, the bus width occupied by the first bus is significantly reduced, resulting in less signal interference when the system performs a 32-bit data write operation, and the signal quality is effectively guaranteed. There is no need to modify the bus width during the 32-bit data write operation, thereby ensuring the normal efficiency of the 32-bit data write operation.
[0064] Optionally, the first bus may split the 32-bit data into two 16-bit data according to a preset write timing, and send the data asynchronously to a first-in-first-out queue.
[0065] Optionally, the preset write timing is: after the write operation is responded to, it is placed in a waiting state until entering the kth clock cycle, and part of the 32-bit data is sent to the first-in-first-out queue to realize the writing of the first 16-bit data; when the first 16-bit data is successfully written, the remaining data in the 32-bit data is sent to the first-in-first-out queue to realize the writing of the second 16-bit data, and k is a positive integer.
[0066] For some examples, see Figure 4In the read timing shown, after the write operation is responded, it is placed in a waiting state until entering the second clock cycle, and part of the 32-bit data is sent to the first-in-first-out queue to realize the writing of the first 16-bit data; when the first 16-bit data is successfully written, the remaining data in the 32-bit data is sent to the first-in-first-out queue to realize the writing of the second 16-bit data.
[0067] exist Figure 4 In the timing diagram shown, emif_cen represents the EMIF interface chip select line, emif_addr[15:0] represents the EMIF bus address line, emif_data[15:0] represents the EMIF bus data line, emif_oen represents the EMIF bus read valid bit, emif_wen represents the EMIF bus write valid bit, 1-14 represent each clock cycle, ADDR_low_16bit represents the bus address of the first 16-bit data, ADDR_high_16bit represents the bus address of the second 16-bit data, DATA_low_16bit represents the first 16-bit data, and DATA_high_16bit represents the second 16-bit data.
[0068] S204: The second bus synchronously obtains two 16-bit data from the first-in-first-out queue to implement a 32-bit data write operation.
[0069] Among them, since the second bus is a 32-bit data bus, when the first-in-first-out queue caches two 16-bit data, the second bus can directly obtain 32-bit data composed of two 16-bit data from the first-in-first-out queue. After obtaining the 32-bit data, the second bus writes the 32-bit data to the external device to realize a 32-bit data write operation.
[0070] It should be emphasized that EMIF's 16-bit asynchronous bus and 32-bit asynchronous bus are both parallel buses, and the bus bandwidth increases with the increase in the number of buses. Therefore, using EMIF's 16-bit asynchronous bus for 32-bit data transmission can save half of the bus width compared to the 32-bit asynchronous bus. While ensuring the normal efficiency of 32-bit data transmission, the signal quality when using EMIF's 16-bit asynchronous bus for 32-bit data transmission will be higher, and the requirements for the electrical characteristics of the signal will be relatively low (that is, there is less signal interference, and there is no need to increase the threshold of related hardware to reduce signal interference).
[0071] Optionally, when the system performs a 16-bit data read operation, the second bus sends the 16-bit data to the first bus.
[0072] Optionally, when the system performs a 16-bit data write operation, the first bus sends the 16-bit data to the second bus.
[0073] It should be noted that since the data bit width of the second bus is 32 bits and the first bus supports reading and writing of 16-bit data, the second bus can send 16-bit data to the first bus to implement a 16-bit data read operation, and correspondingly, the first bus can send 16-bit data to the second bus to implement a 16-bit data write operation.
[0074] The process shown in S201-S204 above, with the help of the first-in-first-out queue provided by the data cache, assists the 16-bit asynchronous bus interface shown in the first bus to achieve 32-bit data transmission with the advanced extensible interface shown in the second bus, thereby improving the 32-bit data reading and writing efficiency of EMIF while ensuring the signal quality of the 32-bit data.
[0075] like Figure 5 As shown, it is a schematic diagram of the architecture of a processor provided in an embodiment of the application, including the modules shown below.
[0076] A master interface module 501 , a data cache module 502 and a slave interface module 503 .
[0077] The master interface module 501 includes a 16-bit asynchronous bus interface for an external device interface, the data cache module 502 includes a first-in-first-out queue, and the slave interface module 503 includes an advanced expandable interface for connecting to an external device.
[0078] The slave interface module 503 is used to send the 32-bit data to the first-in-first-out queue when the processor performs a 32-bit data read operation.
[0079] The main interface module 501 is used to obtain two 16-bit data in sequence from the first-in-first-out queue to implement a 32-bit data read operation.
[0080] The main interface module 501 is also used for: when the processor performs a 32-bit data write operation, the main interface module 501 splits the 32-bit data into two 16-bit data, and asynchronously sends them to the first-in-first-out queue.
[0081] The slave interface module 503 is further used to obtain two 16-bit data in sequence from the first-in-first-out queue to implement a 32-bit data write operation.
[0082] Optionally, the main interface module 501 is specifically used to: asynchronously obtain two 16-bit data from the first-in-first-out queue according to a preset read timing to realize a 32-bit data read operation; wherein, the preset read timing is: after the read operation is responded to, it is placed in a waiting state until entering the nth clock cycle, and then the first-in-first-out queue is accessed to realize the reading of the first 16-bit data; when the first 16-bit data is successfully read, it is placed in a waiting state again until the end of the mth clock cycle, and then the first-in-first-out queue is accessed again to realize the reading of the second 16-bit data; n and m are positive integers, and m is greater than n.
[0083] Optionally, the main interface module 501 is specifically used to: split the 32-bit data into two 16-bit data according to a preset write timing, and send them asynchronously to a first-in-first-out queue; wherein the preset write timing is: when a write operation is responded to, it is placed in a waiting state until entering the kth clock cycle, and part of the 32-bit data is sent to the first-in-first-out queue to implement the writing of the first 16-bit data; when the first 16-bit data is successfully written, the remaining data in the 32-bit data is sent to the first-in-first-out queue to implement the writing of the second 16-bit data.
[0084] Optionally, the slave interface module 503 is further configured to send 16-bit data to the master interface module 501 when the processor performs a 16-bit data read operation.
[0085] Optionally, the master interface module 501 is further configured to send the 16-bit data to the slave interface module 503 when the processor performs a 16-bit data write operation.
[0086] The processor architecture shown above, with the help of the first-in-first-out queue provided by the data cache module, assists the master interface module to achieve 32-bit data transmission with the slave interface module, thereby improving the 32-bit data reading and writing efficiency of EMIF while ensuring the signal quality of the 32-bit data.
[0087] In addition, the functions described above in the embodiments of the present application may be at least partially performed by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.
[0088] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.
[0089] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present application. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.
[0090] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.
Claims
1. A data transmission method based on EMIF, characterized in that: Applied to a system including a first bus, a data cache and a second bus, wherein the first bus includes a 16-bit asynchronous bus interface of an external device interface, the data cache includes a first-in-first-out queue, and the second bus includes an advanced scalable interface for connecting to an external device, the method includes: When the system performs a 32-bit data read operation, the second bus sends the 32-bit data to the first-in-first-out queue; The first bus asynchronously obtains two 16-bit data from the first-in-first-out queue to implement the 32-bit data read operation; When the system performs a 32-bit data write operation, the first bus splits the 32-bit data into two 16-bit data and asynchronously sends them to the first-in-first-out queue; The second bus synchronously obtains two 16-bit data from the first-in-first-out queue to implement the 32-bit data write operation.
2. The method according to claim 1, characterized in that The first bus asynchronously obtains two 16-bit data from the first-in-first-out queue to implement the 32-bit data read operation, including: The first bus asynchronously obtains two 16-bit data from the first-in-first-out queue according to a preset read timing to implement the 32-bit data read operation; Among them, the preset read timing is: after the read operation is responded, it is placed in a waiting state until entering the nth clock cycle, and the first-in-first-out queue is accessed to realize the reading of the first 16-bit data; when the first 16-bit data is successfully read, it is placed in a waiting state again until the end of the mth clock cycle, and the first-in-first-out queue is accessed again to realize the reading of the second 16-bit data; n and m are positive integers, and m is greater than n.
3. The method according to claim 1, characterized in that The first bus splits the 32-bit data into two 16-bit data and sends them asynchronously to the first-in-first-out queue, including: The first bus splits the 32-bit data into two 16-bit data according to a preset write timing, and sends the data to the first-in-first-out queue asynchronously; Among them, the preset write timing is: when the write operation is responded, it is placed in a waiting state until entering the kth clock cycle, and part of the 32-bit data is sent to the first-in-first-out queue to realize the writing of the first 16-bit data; when the first 16-bit data is successfully written, the remaining data in the 32-bit data is sent to the first-in-first-out queue to realize the writing of the second 16-bit data.
4. The method according to claim 1, characterized in that: The method further comprises: When the system performs a 16-bit data read operation, the second bus sends the 16-bit data to the first bus.
5. The method according to claim 1, characterized in that The method further comprises: When the system performs a 16-bit data write operation, the first bus sends the 16-bit data to the second bus.
6. A processor, characterized in that: include: A master interface module, a data cache module and a slave interface module; Wherein, the master interface module includes a 16-bit asynchronous bus interface for an external device interface, the data cache module includes a first-in-first-out queue, and the slave interface module includes an advanced scalable interface for docking with an external device; The slave interface module is used to: send the 32-bit data to the first-in-first-out queue when the processor performs a 32-bit data read operation; The main interface module is used to: obtain two 16-bit data from the first-in-first-out queue in sequence to implement the 32-bit data read operation; The main interface module is also used for: when the processor performs a 32-bit data write operation, the main interface module splits the 32-bit data into two 16-bit data and asynchronously sends them to the first-in-first-out queue; The slave interface module is also used to obtain two 16-bit data in sequence from the first-in-first-out queue to implement the 32-bit data write operation.
7. The processor according to claim 6, characterized in that The main interface module is specifically used for: According to a preset read timing, asynchronously obtain two 16-bit data from the first-in-first-out queue to implement the 32-bit data read operation; Among them, the preset read timing is: after the read operation is responded, it is placed in a waiting state until entering the nth clock cycle, and the first-in-first-out queue is accessed to realize the reading of the first 16-bit data; when the first 16-bit data is successfully read, it is placed in a waiting state again until the end of the mth clock cycle, and the first-in-first-out queue is accessed again to realize the reading of the second 16-bit data; n and m are positive integers, and m is greater than n.
8. The processor according to claim 6, characterized in that The main interface module is specifically used for: According to the preset write timing, the 32-bit data is split into two 16-bit data, and sent asynchronously to the first-in-first-out queue; Among them, the preset write timing is: when the write operation is responded, it is placed in a waiting state until entering the kth clock cycle, and part of the 32-bit data is sent to the first-in-first-out queue to realize the writing of the first 16-bit data; when the first 16-bit data is successfully written, the remaining data in the 32-bit data is sent to the first-in-first-out queue to realize the writing of the second 16-bit data.
9. The processor according to claim 6, characterized in that: The slave interface module is further used to send 16-bit data to the master interface module when the processor performs a 16-bit data read operation.
10. The processor according to claim 6, characterized in that The master interface module is also used to send 16-bit data to the slave interface module when the processor performs a 16-bit data write operation.
Citation Information
Cited By
Bus data transmission method for connecting CPLD and FPGA and bus
CN119759828A
